• The Korean Journal of Applied Statistics
• /
• v.7 no.2
• /
• pp.173-182
• /
• 1994

By applying slope estimator under the arbitrary error distributions proposed by Han(1993), if we define regression quantiles to give upper and lower trimming part and blocks of data, we show the proposed slope estimator has asymptotically efficient slope estimator when the number of regression quantiles to from blocks of data goes to sufficiently large.

• The Korean Journal of Applied Statistics
• /
• v.23 no.2
• /
• pp.375-382
• /
• 2010

In this study, we propose a robust estimator of the multivariate location parameter by means of the spatial median based on data trimming which extending trimmed mean in the univariate setup. The trimming quantity of this estimator is determined by the bootstrap method, and its covariance matrix is estimated by using the double bootstrap method. This extends the work of Jhun et al. (1993) to the multivariate case. Monte Carlo study shows that the proposed trimmed spatial median estimator yields better efficiency than a spatial median, while its covariance matrix based on double bootstrap overcomes the under-estimating problem occurred on single bootstrap method.

• Transactions of Materials Processing
• /
• v.15 no.4 s.85
• /
• pp.281-288
• /
• 2006

Most of automobile member parts experience severe springback problems because of their complicated shape and high yielding strength. Now it becomes imperative to develop an effective method to resolve these problems. However, there remain several obstacles to get accurate estimation of dimensional shape. Especially the effective algorithms to simulate sheet metal forming processes including drawing, trimming, flanging and springback is demanded for the multi stage simulation of automobile member parts. In this study, for the purpose of accurate springback calculation, a simulation program which is robust in springback analysis is developed. Favorable enhancement in computation time for springback analysis by using latest equation solving technique and robust solution convergence by continuation method are achieved with the program. In analysis, the multi processes of rear side member are simulated to verify the system. For the evaluation of springback accuracy practically, all conditions including boundary conditions for springback analysis and inspection conditions for dimensional accuracy are applied. The springback results of simulations show good agreement with the experiments.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2004.11a
• /
• pp.71-78
• /
• 2004

Most of member parts have experienced severe springback problems because of their open shape Now it becomes imperative to develop an effective method, which can resolve these problems. However, there remain several obstacles to get accurate estimation of shape error. In analysis, we have to analyze the total process including forming, trimming and flanging. Furthermore, it is another challenge to compare the computed result with the real shape. In this study we developed an analysis program for the springback analysis. We could achive a big enhancement in computation time in springback analysis by using latest equation solving technique and could get a more robust solution conversence by contination method. We have approached this problem in two steps. In the first step, we analyzed forming stage to solve tearing and wrinkling problems. In the second step, we have analyzed full process and have done springback analysis with the same boundary condition as field measuring conditions. We have investigated the accuracy of springback analysis in terms of gap and flush used for insfection of real autobody panels. We found good and effective agreement with the observed results.